Back to Main Conference 2002
LREC 2002main
Using the Text Corpus to Create a Comprehensive List of Phrasal Verbs
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC 2002)
Abstract
The paper describes extraction of Estonian multi-word verbs from text corpora, using a language- and task-specific software tool SENVA, which is based on a statistical language-independent software tool SENTA (Dias et al, 2000). The outcome is a comprehensive list of 16,000 phrasal verbs. We describe the extraction tool, manual post-editing principles, and evaluate the outcome in terms of precision and recall, comparing the results with man-made electronic dictionaries, and with the results of a manual extraction experiment of a sub-set of the MWV-s.